Reserved topic scholarships
Department of Information Engineering and Computer Science
This project will focus on the design and development of lightweight machine learning models for sensor systems to be used in smart buildings. We will investigate lightweight black-box (e.g., neural networks) and white-box (e.g., decision trees) models, and combinations thereof. Moreover, we will use Neural Architecture Search and evolutionary algorithms to derive optimally designed models that take into account possible computational and energy constraints on the nodes of the distributed system. We will also study the explainability of those models. The proposed research will lie at the intersection of the following topics and can be structured considering the profile and interests of the candidate: Machine Learning (Tiny Machine Learning), Evolutionary Computation, Distributed Systems and Algorithms, Embedded Systems (Low-Power Computing), Sensor Networks (Low Power Communications and Networking). Previous experience in at least one of these topics is considered a plus.
Contact: Giovanni Iacca giovanni.iacca [at] unitn.it
Recent advances in large vision-language models have revolutionized the image classification paradigm. Despite showing impressive zero-shot capabilities, a pre-defined set of categories is assumed at test time for existing models such as CLIP for composing the textual prompts. However, such assumption can be impractical when the semantic context is unknown and evolving. This PhD project will investigate novel approaches for fine-grained and adaptive visual recognition. Approaches will first focus on images and then on videos.
Contact: Elisa Ricci e.ricci [at] unitn.it
This PhD will pursue the development of hybrid human-machine learning and decision making strategies for medical decision making. The project will focus on team decision making for the treatment of abdominal aortic aneurysms, and will be conducted within the TANGO Horizon EUROPE RIA project.
Contact: Andrea Passerini andrea.passerini [at] unitn.it
This PhD will pursue the development of neuro-symbolic machine learning architectures supporting perception, reasoning, introspection, and debugging. The project will revolve around the design of strategies for ensuring these systems satisfy trustworthiness desiderata and will be conducted within the TANGO Horizon EUROPE RIA project.
Contact: Andrea Passerini andrea.passerini [at] unitn.it
In generative models, the challenge lies in sampling and forming images from an original distribution, which can be reframed as a problem of transforming one distribution into another. To address this, some generative models, including normalizing flow, score matching models, and the recent flow matching methods are introduced, involving a mapping between a fixed distribution (Gaussian distribution) and a target distribution. The Schrödinger bridge (SB) problem considers the most likely path between an initial and target distribution under a given reference process. In this project, we plan to develop a new approach to tackle the Schrödinger Bridge problem within the context of flow matching. This envisioned approach involves incorporating concepts from fluid dynamics into the Schrödinger Bridge framework, aiming to establish an optimal pathway for transporting data from the initial distribution to the desired target distribution. This integration has the potential to enhance the model's interpretive clarity, improve the model performance and simultaneously streamline the computational complexity associated with its implementation.
Contact: Niculae Sebe niculae.sebe [at] unitn.it
Automated software and configuration repairs aims at recovering from security vulnerabilities and is a promising way to support systems with a continuous development and deployment pipeline. Artificial Intelligence (AI) methods, such as machine and deep learning, explainability techniques, generative AI, and evolutionary algorithms, can be leveraged to: (i) enhance state-of-the-art of program repair techniques by combining knowledge extracted from different sources (e.g., code repositories, requirement specifications, system executions); and (ii) improve the existing vulnerability exploitation and software validation techniques.
Within the Ph.D., the candidate will work (a) by learning and combining knowledge from heterogeneous system artifacts and (b) by comparing and enriching existing program repair techniques with AI methods. The Ph.D. work will involve theoretical,
methodological and empirical aspects, ranging from the capability to design new solutions up to the development of new tools and their experimental validation. The work will be partially carried out in the context of the Sec4AI4Sec Horizon Europe project and in collaboration with some of its industry partners most notably SAP, Airbus, Thales, and FrontEndArt.
Contact: Fabio Massacci fabio.massacci [at] unitn.it; Alessandro Marchetto alessandro.marchetto [at] unitn.it
The research activity will be centered on the application of the Digital Twin concept to mobile networks, and 5G/6G networks in particular.
In a first phase, methodologies able to create the Digital Twin of such networks will be studied, based on the interfaces offered by 5G networks (and 6G, in the future) as well as traffic and device state measurements. Once the accuracy of such Digital Twin representations will be evaluated, the research will then focus on the usage of Digital Twins in scenarios of integration of Machine Learning and Artificial Intellingece methodologies in 5G/6G networks.
Contact: Fabrizio Granelli fabrizio.granelli [at] unitn.it
Software testing aims at discovering and preventing bugs and security vulnerabilities and is a promising way to verify systems with a continuously evolving systems. Artificial Intelligence (AI) methods, such as machine and deep learning, generative AI, explainability techniques, and evolutionary algorithms can be leveraged to: (i) enhance state-of-the-art testing techniques by combining knowledge extracted from different sources (e.g., code repositories, requirement specifications, system executions), and (ii) increase testing automation.
Within the Ph.D., the candidate will work (a) by learning and combining knowledge from heterogeneous system artifacts and (b) by comparing and enriching modern testing techniques with AI methods. The Ph.D. work will involve theoretical, methodological and empirical aspects, ranging from the capability to design new solutions up to the development of new tools and their experimental validation.
The work will be partially carried out in the context of the Sec4AI4Sec Horizon Europe project and in collaboration with some of its industry partners most notably SAP, Airbus, Thales, and FrontEndArt
Contact: Fabio Massacci fabio.massacci [at] unitn.it; Alessandro Marchetto alessandro.marchetto [at] unitn.it
The research project involves the study and proposal of techniques to counter and make it more difficult to attack and manipulate the behaviour of machine learning algorithms. The research also includes the study of metrics with which the degree of difficulty introduced by these techniques can be measured. Finally, the research also includes the application of the methods and techniques introduced in cyber security contexts and scenarios
Contact: Bruno Crispo bruno.crispo [at] unitn.it
This PhD research grant has the objective of designing, executing and evaluating highly qualified educational initiatives within the domain of higher education in Computer Science - and more in general, Engineering disciplines – while exploring the following research spaces:
(1) How can we create technical education that is resilient to technological obsolescence?
(2) What opportunities are there for computing education in embracing potential paradigm shifts generated by LLMs and other AI products?
(3) How can we create more technically, socially, environmentally, and pedagogically sustainable digital education?
Candidates will work on developing innovative teaching based on active learning, with a particular focus on methods such as Challenge-Based Learning. All activities will be contextualised in the frame of the many European collaborations active within the research group. Ideal candidates will have (or will aim to develop) an interdisciplinary profile, combining a computer science core expertise with sound grounding on education theory and innovation and entrepreneurship.
Contact: Maurizio Marchese maurizio.marchese [at] unitn.it
Large Language Models (LLMs) have achieved astonishing performance on language tasks, both on natural language understanding and natural language generation. Their reasoning capabilities are still under debate. The winner of the grant will work on analyzing and improving LLMs on information-seeking tasks. Such tasks involve a tie connection between language generation and reasoning, therefore they are a suitable test-bed to advance on the intersection between these core abilities of AI systems.
Contact: Raffaella Bernardi raffaella.bernardi [at] unitn.it
Department of Information Engineering and Computer Science - Italian Space Agency
D1 - Methodologies based on machine learning and artificial intelligence for the automatic analysis of radar sounder data (project: ASI EnVision, Agreement n.2022-23-HH.0, CUP no. F63C22000650005) (1 grant)
The research of this grant is related to the use of artificial intelligence and machine learning techniques for the analysis of data acquired by planetary radar sounders. Radar sounders operate from satellite platforms and acquire data related to the subsurface of celestial bodies that can results in groundbreaking science results. This activity will be developed in the framework of the EnVision mission of the European Space Agency (ESA) (for more information refer to https://envisionvenus.eu/envision/) and in particular on the Sub-surface Radar Sounder (SRS) on board the mission. SRS has the objective to investigate the shallow Venus subsurface (up to few hundred meters) to reveal its mysteries by studying the tectonic, volcanism, impacts, relation between surface and subsurface features, etc.
The PhD research activity will include at least one of the following topics:
- Novel methodologies and techniques based on machine learning and artificial intelligence for the analysis radar sounder data.
- Simulations for the analysis of the performance of the radar versus different Venus scenarios by integrating traditional simulation techniques with machine learning approaches.
- Test campaigns with ground penetrating radar from drone/helicopter on terrestrial sites considered as analogous of Venus subsurface.
Research will be developed at the Remote Sensing Laboratory (https://rslab.disi.unitn.it/)
Contact: Lorenzo Bruzzone lorenzo.bruzzone [at] unitn.it
Department of Information Engineering and Computer Science | Department of Industrial Engineering - Q@TN Project
The research project has the goal to understand and characterize quantum devices reliability. Both intrinsic noise and the impact with external sources of faults (such as natural radiation) will be considered. Specifically, the PhD candidate, through physical simulations and radiation experiments, will define and formalize the radiation-induced fault model and evaluate the fault probability in quantum chips. Moreover, the candidate will collaborate with the research group to track fault propagation in quantum circuits and evaluate the fault impact on the circuit output correctness. Finally, thanks to the achieved results and the acquired knowledge, the candidate will collaborate to exploit quantum computing potential to design efficient and effective circuit-level hardening techniques against radiation-induced transient faults.
Contact: Paolo Rech paolo.rech [at] unitn.it Flavio Vella flavio.vella [at] unitn.it
Fondazione Bruno Kessler (FBK)
The Internet of Things (IoT) is enabling and multiplying the point of collection of multimodal data such as audio, video and environmental data, typically processed in the cloud where potentially infinite computational power is available. However, this comes at the cost of bandwidth, energy and privacy. Recent research in the so-called tinyML domain is tackling the challenge of bringing artificial intelligence to the end-devices, thus limiting the need to stream data to the cloud and implementing the distributed intelligence paradigm in the cloud-edge continuum. Thus, novel approaches to enable AI, typically computationally demanding, on resource-limited devices are needed. Exciting research scenarios are emerging to enable inference at the edge, ranging from distillation, quantization, or neural architecture search strategies to the fusion of software techniques with innovative hardware supporting tinyML. The complexity grows when we consider shifting not only inference but also learning to the edge to harness the opportunities offered by connected, distributed devices. The research proposed will focus on one or more of the following goals: (i) Develop novel hardware and software approaches to optimize AI on energy-efficient embedded devices, with a particular emphasis on audio processing and computer vision, while also considering other domains. (ii) Explore the potential of distributing and integrating intelligence from heterogeneous nodes in an IoT environment. (iii) Demonstrate the benefits of these approaches in real-world application scenarios, such as those encountered in smart cities.
This interdisciplinary research at the intersection of Artificial Intelligence, Embedded Systems, Distributed Computing, and Low-power Hardware will take into account the candidate's profile and interests, contributing to the development of innovative solutions for real-world challenges. The candidate will have the opportunity to work with cutting-edge technology, gain valuable experience in interdisciplinary collaboration, and make significant contributions to the field of tiny machine learning.
Contact: Elisabetta Farella efarella [at] fbk.eu
Social learning strategies are a key component of human intelligence and of our ability of learning from and collaborating with other humans in their environment. Inspired by this, some initial research efforts are enabling embodied AI agents with social and cooperative skills, thus permitting them to coordinate and collaborate with and to learn from other agents and humans. The goal of this PhD thesis is to devise innovative cooperative learning algorithms to support navigation of embodied AI agents in dynamic complex environments populated by other agents and humans, and to learn how to interact and to communicate with other heterogenous agents to learn collaboratively world models. The ideal candidate would have research interest in cooperative and embodied AI, multi-agent deep reinforcement learning, neuro-symbolic approaches, etc. The candidate will have the possibility of working within the ELLIS network and in collaboration with top international and national universities.
Contact: Bruno Lepri lepri [at] fbk.eu Luciano Serafini serafini [at] fbk.eu
Clinical neuroscience is playing a key role in the understanding of the brain with data of pathological alterations. The detection of anomalies in the brain structure and function is a crucial step not only for diagnosis and prognosis but also to decode the connectome of the human brain. Data driven approaches are providing promising results to characterize the patterns of the healthy brain. The challenge is to disentangle the intrinsic interindividual differences in the brain structure and function with respect to alterations related to cognitive impairment.
The research objective is to investigate the most innovative techniques of Artificial Intelligence, such as geometric deep learning, to translate the knowledge of connectivity structures from a healthy population to the individual patients of a clinical study. The ultimate goal is the development of computational methods to support the detection of altered structures in the connectome affected by brain disorders.
Contact: Paolo Avesani avesani [at] fbk.eu
This PhD position calls for research into "foundation models," a type of deep learning neural network. These models, trained using vast amounts of data, serve as starting points for various tasks including, but not limited to, classification, regression, segmentation, and detection. However, the application of these models to the understanding of 3D scenes presents a challenge due to the unique characteristics of the training data. The proposed research aims to bridge this gap. The PhD candidate will primarily be tasked with exploring and constructing innovative vision algorithms rooted in deep learning and based on foundation models. The goal is to develop algorithms that can be effectively and flexibly utilised across diverse data types and domains.
Contact: FabioPoiesi poiesi [at] fbk.eu
In spite of the recent progress in speech technologies, processing and understanding conversational spontaneous speech is still an open issue, in particular in presence of challenging acoustic conditions as those posed by dinner party scenarios. Although enormous progresses have been made recently in a variety of speech processing tasks (such as speech enhancement, speech separation, speech recognition, spoken language understanding), targeting also multi-speaker speech recognition, a unified established solution is still far from being available. Moreover, the computational complexity of current approaches is extremely high, making an actual deployment in low-end or IoT devices not feasible in practice.
The candidate will advance the current state-of-the-art in speech processing (in particular for separation, enhancement and recognition) towards developing a unified solution, possibly based on self-supervised or unsupervised approaches, for automatic speech recognition in dinner party scenarios, as those considered in the CHiME challenges (https://arxiv.org/abs/2306.13734).
Contact: Alessio Brutti brutti [at] fbk.eu
Planning - devising a strategy to achieve a desired objective - is one of the basic forms of intelligence, with applications in autonomous robotics, logistics, flexible production, and many other fields. Historically, planning research has followed a general-purpose framework: a generic engine searches for the strategy by reasoning on the problem statement. Despite substantial progress in recent years, domain-independent planning still suffers from scalability issues and fails to deal with real-word problems. The alternative is to devise ad-hoc, domain-specific solutions that, although efficient, are costly to develop, rigid to maintain, and often inapplicable in non-nominal situations.
The PhD student will study the foundations of an innovative approach to Planning that will be domain-independent and efficient at the same time. The idea is to adopt a framework based on Reinforcement Learning, where a domain-independent planner is specialized with respect to the domain at hand. This research project will advance the state of the art in planning beyond the “efficiency vs flexibility” dilemma and provide effective techniques to be validated on real-world use-cases.
Contact: Andrea Micheli amicheli [at] fbk.eu
Conversational agents are experiencing a surge in interest given the continuous release of new models and the ever evolving scenario of NLG. Still, the actual focus is mainly on model size, training data size and prompt engineering. The interaction of these elements with related aspects, such as decoding strategies, knowledge guided generation, data quality, knowledge distillation -just to mention a few- can help in improving the models, especially for better factuality, reducing hallucination and increasing coherence among dialogue turns. The goal of this PhD Thesis is to overcome the shortcomings of present large language models by incorporating novel strategies for better generation
Contact: Marco Guerini m.guerini [at] fbk.eu
In recent years, there has been a significant increase in demand for secure and efficient systems to process data. In-network computing has emerged as a promising solution for offloading computation tasks, reducing latency, and relieving the workload of connected computing nodes. This technology uses smart network interface cards (smartNICs) to perform computation tasks on the network. However, limited adoption of this technology is due to the maturity of the software stack and related programming models, particularly for security applications.
This PhD scholarship aims to investigate many aspects of enabling in-network computing as a newer paradigm for solving security challenges, including cryptography. After conducting a literature review to identify relevant research and industry efforts in this area, focusing on existing systems such as NVIDIA Bluefield and programming models like DOCA or sPIN, the PhD candidate will identify challenges associated with adopting an in-network computing model for security and propose novel technical solutions. Additionally, the PhD candidate will conduct experimental evaluations to measure the performance and security of the proposed solutions (e.g., cryptographic algorithms implemented on smartNICs) and compare these results with traditional approaches. The findings of this research can guide future research and development in this area and can be applicable to industries that require secure and efficient data processing.
Contact: Domenico Siracusa dsiracusa [at] fbk.eu
Techniques based on formal methods for the verification and validation of embedded and safety-critical software systems are becoming increasingly important, due to the growing complexity and importance of such systems in every aspect of modern society. Despite the major progress seen in the last twenty years, however, the application of formal methods in embedded software remains a challenge in practice, due to factors such as the interplay between computation and physical aspects and the increasing complexity of the software and its configurations.
This project will investigate novel techniques for the application of formal methods to the design, verification, and validation of embedded software, with particular emphasis on safety-critical application domains such as railways, automotive, avionics, and aerospace. The techniques considered will include a combination of automated and interactive theorem proving, satisfiability modulo theories, model checking, abstract interpretation, and deductive verification. Examples of the problems tackled during the project include the formal verification of functional requirements expressed in temporal logics, automated test-case generation, efficient handling of parametric/multi-configuration software systems and product lines, and the verification of software operating in a physical environment, subject to real-time constraints. Importantly, in addition to researching novel theoretical results, a significant part of the project activities will be devoted to the implementation of the techniques in state-of-the-art verification tools developed at FBK and their application to real-world problems in collaboration with our industrial partners.
Contact: Alberto Griggio griggio [at] fbk.eu
Hybrid systems are formal models combining discrete and continuous-time dynamic behaviors. They can be found in various applications such as robotics, control systems, cyber-physical systems, and transportation systems. Formal methods for hybrid systems provide a powerful set of techniques for designing, analyzing, and verifying the behavior of complex systems that exhibit both continuous and discrete behaviors. These techniques can be used to ensure the correctness and safety of the system and to detect design flaws and bugs early in the development cycle. This project will investigate new formal methods to prove properties of hybrid systems integrating model checking, automated theorem, and numerical analysis for control theory. Different aspects of hybrid systems will be considered including temporal properties, diagnosability and epistemic properties, reliability and robustness to faults. Compositional reasoning and proof synthesis will be also considered. The new methods will be implemented and evaluated on industrial benchmarks derived by industrial collaboration of FBK in various application domains such as space, avionics, autonomotive, railyways, and energy.
Contact: Stefano Tonetta tonettas [at] fbk.eu
Industrial systems are reaching an unprecedented degree of complexity. The process of designing a complex system is expensive, time consuming and error-prone. Moreover, the design process has to guarantee not only the functional correctness of the implemented system, but also its dependability and resilience with respect to run-time faults. Hence, the design process must characterize the likelihood of faults, mitigate possible failures, and assess the effectiveness of the adopted mitigation measures.
Formal methods have been increasingly used over the last decades to deal with the shortcomings of designing a complex system. Formal methods are based on the adoption of a formal, mathematical model of the system, shared between all actors involved in the system design, and on a tool-supported methodology to aid all the steps of the design, from the definition of the architecture down to the final implementation in HW and SW. Formal methods include technologies such as model checking, an automatic technique to symbolically and exhaustively analyze all possible executions of the system in the formal model, in order to detect design flaws as early as possible. Model checking techniques have been recently extended to assess the safety and dependability characteristics of the design, and for system certification.
The objective of this study is to advance the state-of-the-art in system design using formal methods. This includes adapting and extending the system design methodology, investigating improved versions of state-of-the-art routines for verification and safety assessment of complex systems, and developing novel extensions to address open problems. Examples of such extensions include novel techniques for contract-based design and contract-based safety assessment, advanced techniques for formal verification based on compositional reasoning, the analysis of the timing aspects of fault propagation, the characterization of transient and sporadic faults, the analysis of the effectiveness of fault mitigation measures in presence of complex fault patterns, and the modeling of analysis of systems with continuous and hybrid dynamics.
This study will exploit the challenges and benchmarks defined in various industrial projects carried out at FBK.
Contact: Marco Bozzano bozzano [at] fbk.eu
Planning and scheduling are techniques to automate and/or optimize decision-making. There is a breadth of applications that can benefit from the application of this kind of technique including (but not limited to) robotics, flexible manufacturing, logistics and people management. The aim of this PhD scholarship is to investigate and reinforce the applicability of this kind of technique considering the whole spectrum of domains that recently emerged from the AIPlan4EU (aiplan4eu-project.eu) project. The candidate will research innovative approaches and algorithms to improve the performance, usability and/or relevance of planning and scheduling techniques deployed in diverse scenarios, having the unique possibility to work and experiment with real-world scenarios of planning already deployed by the project.
Contact: Andrea Micheli amicheli [at] fbk.eu
Applications are invited for a Ph.D. opportunity focused on secure data spaces for trustworthy data sharing in digital agriculture. The research aims to develop robust platforms for data sharing, privacy, and integrity in the agricultural landscape. Applicants should have a background in computer science or data management, with familiarity in agricultural systems and/or practices, data analytics, machine/deep learning, and algorithm design, validation, and benchmarking.
Contact: Massimo Vecchio mvecchio [at] fbk.eu Fabio Antonelli fantonelli [at] fbk.eu
In modern and heterogeneous learning environments, the one-size-fits-all approach is proven to be fundamentally flawed. Individualization through adaptivity is crucial to nurture individual potential, needs and motivational factors. The goal of this PhD thesis is to investigate the potential of combining gamification mechanics and adaptive personalized learning, analyzing the impact in terms of students’ achievements, participation and motivation. In particular, the PhD candidate will investigate AI-based theories and techniques for the development and validation of an open, content-agnostic, and extensible platform for personalized playful learning. The platform will be validated in different formal and informal educational contexts. The ideal candidate has a background in Computer Science or Cognitive Science. Game design, educational and cognitive psychology, motivation theories, knowledge on designing and conducting experimental studies, experience with quantitative and qualitative data analysis techniques are a plus for the application and should be acquired during the Phd training.
Contact: Antonio Bucchiarone bucchiarone [at] fbk.eu
With an increasing availability and need of point clouds and 3D urban models, the inclusion of semantic information is becoming more and more important, in order to facilitate the usage and exploitation of such data. Traditional deep learning methods applied to 3D geospatial data suffer of generalisation, adaptation and explainability. Data annotation is also a major bottleneck, being time consuming and prone to errors.
The research topic should work with photogrammetric, RGB-D and LiDAR 3D data and:
(i) investigate self-supervised and unsupervised 3D classification methods, including few-shot or zero-shot learning
(ii) design models that can better adapt and generalise among scenarios
(iii) make 3D semantic segmentation results more explainable.
This research position calls for a highly motivated and skilled researcher who possesses a good combination of computer science, AI and geomatics knowledge.
Contact: Fabio Remondino remondino [at] fbk.eu
A better understanding of Earth climate and evolution relies on a better understanding or other planets. In 2023 European Space Agency (ESA) launched the JUpiter ICy moons Explorer (JUICE) mission to the Jovian system, and the development of the ESA EnVision mission to Venus is under development. Both missions carry on board a radar sounder instrument for subsurface sensing of planetary bodies. In the context of these two projects we are looking for candidates willing to design methodologies for sub-surface radar image processing and analysis. The outcome of this activity will contribute in improving the understanding of planetary subsurface structures, and their correlation to history and climate, as well as of Earth.
The candidate will be requested to design and develop novel methodologies based on artificial intelligence, deep learning and machine learning for information extraction, segmentation, classification, target detection, noise reduction and change detection in radar and radar sounder images.
Besides the requirements established by the rules of the ICT school, preferential characteristics for candidates for this scholarship are:
• master degree in Electrical Engineering, Communication Engineering, Computer Science, Mathematics or equivalents;
• knowledge in pattern recognition, deep learning, image/signal processing, statistic/remote sensing/radar.
This grant is funded by project ASI EnVision ph.B1 - “Attività scientifiche per il radar sounder di EnVision fase B1” — CUP F63C22000650005.
Contact: Francesca Bovolo bovolo [at] fbk.eu
This research aims to develop an innovative framework that combines optical sensors (e.g. cameras and LiDAR) and Internet of Things (IoT) technologies for real-time monitoring of civil infrastructures (e.g. bridges, buildings, dams, etc.). This research position calls for a highly motivated and skilled researcher who possesses a good combination of software expertise, hardware integration knowledge and fast prototyping capabilities. Therefore the successful candidate is supposed to have a strong ability to bridge software and hardware components, along with the agility to rapidly prototype innovative, reliable and replicable solutions. The interdisciplinary Phd is expected to provide a secure, replicable and reliable framework whose findings will be applicable to various industries, including transportation, construction, mining, etc., and could have significant implications for public safety and economic development.
Contact: Fabip Remondino remondino [at] fbk.eu
Fondazione Edmund Mach - Department of Information Engineering and Computer Science - Italian Space Agency
The research of this grant will be focused on the analysis of multitemporal remote sensing images for detecting abrupt and subtle changes in forest areas. The main interest is in developing novel methods that can exploit both hyperspectral and SAR images to identify disturbances in the forest (e.g., vegetation stress, infestations). Part of the activity will be developed in the framework of the AFORISMA project, which is funded by Italian Space Agency and is focused on the development of novel methods for the analysis of PRISMA hyperspectral and multitemporal images in forestry.
Research will be developed partila at Fondazione Edmund Mach and partially at the Remote Sensing Laboratory (https://rslab.disi.unitn.it/) of the University of Trento
Contact: Lorenzo Bruzzone lorenzo.bruzzone [at] unitn.it Damiano Gianelle damiano.gianelle [at] fmach.it
Toyota Motor Europe NV/SA - Department of Information Engineering and Computer Science
With the existence of large models and their strong performance many applications of AI are unlocked. A main obstacle is the size of these models which prevents their easy deployment on edge devices. Knowedlge distillation, network pruning and quantization are promising techniques to transfer the knowledge embedded in a large model to a smaller model. The PhD project will focus on the development of novel frameworks for reducing the computational cost of large deep models in challenging scenarios that involves learning under domain and semantic shift.
Contact: Elisa Ricci e.ricci [at] unitn.it
Additional positions supported by a scholarship under the Italian National Recovery and Resilience Plan (NRRP) and Complementary National Plan (CNP), Mission 4, component 2
Human-Machine-Teaming refers to humans and machines collaborating together for pursuing goals. Along the path to achieve these goals, making decision is a crucial step that should be carefully planned. A particularly challenging scenario is decision making in surgical operating rooms, a high-risk and complex socio-technical environment in which multiple agents work collaboratively as a team to provide safe and excellent care to patients. This PhD will focus on the automated analysis of teams in surgical scenarios to build AI coaching strategies for decision making.
Contact: Andrea Passerini andrea.passerini [at] unitn.it
B6 - Systems, signal processing algorithms, and communication protocols for networking, localization and security in underwater acoustic networks (iNEST - Interconnected Nord-Est Innovation Ecosystem, SPOKE 8 -
CUP no. E63C22001030007) (1 grant)
The student will design efficient network protocols including, e.g., medium access, routing, and error control, for underwater acoustic networks in support of localization and multi-hop data retrieval. The protocols will include security features that take into account the bandwidth and energy constraints of underwater devices, e.g., through physical layer security techniques.
Contact: Paolo Casari paolo.casari [at] unitn.it
Nowadays, smartphone are pervasive and equipped with many sensing and communication technologies. These can be exploited to automatically accrue fine-grained information about the context of the user, spanning both the digital and physical worlds. For instance, interactions with other users can be monitored online, e.g., by interfacing with messaging apps, but also in the physical world, e.g., via technologies enabling outdoor and/or indoor proximity and localization. Nevertheless, how to accurately and efficiently capture context in the wild is still an open problem.
At the same time, machine learning approaches offer today an unprecedented opportunity to exploit the plethora of context data potentially accrued. This is typically used for offline analysis (e.g., by sociologists or medical doctors). However, a more intriguing opportunity is to exploit context data at runtime, to provide the user with timely insights, nudging behavior, or application services with innovative context-based modalities.
The PhD student will work at the crossroads of these complementary perspectives, with an end-to-end, holistic view. We envision the work to begin with the lower system layers enabling accurate detection of interactions in the physical world, and their integration in an already existing context-based toolchain focused on digital ones. Once this crucial building block is developed, the next steps will focus on exploiting it as part of the higher-layer reasoning required for runtime interaction and feedback to the user. Both aspects will entail system development as well as validation in-field in existing real-world settings available to the research groups involved.
Contact: Gian Pietro Picco gianpietro.picco [at] unitn.it
Sensing of behavioral patterns. This project will focus on the collection and interpretation of vision as well as Radio Frequency (RF) data for the comprehension of indoor user behavior.
Contact: Fausto Giunchiglia fausto.giunchiglia [at] unitn.it
The successful candidate will develop and validate quantitative ultrasound imaging techniques for tissue characterization by conducting research on simulated, experimental, pre-clinical, and clinical data.
Particular attention will be focused on the characterization of lung tissue alterations by means of quantitative lung ultrasound spectroscopy. Thanks to the availability of simulated, experimental, and clinical data acquired through the deployment of dedicated multispectral imaging methods, the impact of novel spectral features on augmenting lung ultrasound specificity in the differential diagnosis of lung diseases will be investigated.
Research will also be conducted on photoacoustic spectroscopy by means of pre-clinical data in collaboration with the National Research Council.
Contact: Libertario Demi libertario.demi [at] unitn.it